From the series: MATLAB and Simulink Robotics Arena
Kris Fedorenko, MathWorks
Connell D'Souza, MathWorks
With a focus on student robotics competitions, Connell D'Souza and Kris Fedorenko show you how to get started with black box modeling. You will be exposed to basic modeling concepts, and see a demonstration of the system identification process on real-life data from Blue Robotics. Having a model allows you to design and test a controller as well as model a larger system—important steps for preparing your robot for a competition. You can find all the data used in this video on MATLAB Central’s File Exchange.
The System Identification app enables you to perform all stages of modeling such as importing and preprocessing the data, trying out different model structures, and evaluating the resulting models. Two datasets of input and output data for a T200 Blue Robotics Thruster are used to demonstrate the modeling process. Connell and Kris show how to process the data by removing means and filtering out noise. Several models are then created using simple linear model structures like state space model and transfer function, illustrating that modeling is an iterative process. You will also learn how to use validation data to evaluate your models.
After this video, you should be able to create a reasonable model for your own hardware component. As Connell and Kris underline, you would need to collect good-quality input and output data for both estimation and validation, start with simpler model structures, and keep iterating until you achieve good results. You might find the following links helpful:
Introduction to Robotic Systems Meet MATLAB and Simulink Robotics Arena team members Sebastian Castro and Connell D’Souza as they discuss designing a robotic system and the support provided to robotics student competition teams.
Contact Modeling with Simulink Sebastian Castro and Ed Marquez Brunal introduce the fundamentals of mechanical contact modeling and simulation with Simulink, as well as show examples for automotive and robotics applications.
Contact Modeling with Simscape Sebastian Castro and Ed Marquez Brunal discuss various approaches and online resources for modeling mechanical contact and friction forces using Simulink, Simscape, and Simscape Multibody.
Estimating Direction of Arrival with MATLAB Stephen Cronin from the Robotics Association at Embry-Riddle Aeronautical University demonstrates how to detect the direction of arrival of an underwater acoustic signal using MATLAB.
Optimizing Walking Robot Trajectories Join Sebastian Castro as he shows you how you can use MATLAB and the Global Optimization Toolbox to find optimal motion trajectories for a Simulink model of a walking robot.
Beat Tracking with MATLAB for Signal Processing Cup Jeremy Bell, Angus Keatinge, and James Wagner of The University of New South Wales (UNSW Sydney) discuss their team’s winning entry to the IEEE Signal Processing Cup 2017.
Getting Started with MATLAB and ROS Join Sebastian Castro and Pulkit Kapur as they show how Robotics System Toolbox can help you connect MATLAB and the Robot Operating System (ROS).
Getting Started with Simulink and ROS Join Sebastian Castro and Pulkit Kapur as they show how Robotics System Toolbox can help you connect Simulink and the Robot Operating System (ROS).
Deploying Standalone ROS Nodes from Simulink Join Sebastian Castro and Pulkit Kapur as they show how automatic code generation tools can help you deploy algorithms developed in MATLAB and Simulink to run in the Robot Operating System (ROS).
Building Graphical Aircraft Design Tools Build interactive design tools to reduce development time. Zachary Leitzau from Embry-Riddle Aeronautical University demonstrates the use of a self-built app to help design a model airplane.
Simulating Quadcopter Missions with Simulink and ROS Simulation is a great way to test and tune control algorithms for quadcopters. Julien Cassette talks about using Simulink, Robotics Operating System (ROS), and Gazebo to simulate quadcopter missions from student competitions.
Airframe Optimization with MATLAB Follow Joshua Williams from Cornell University Unmanned Air Systems (CUAir) as he demonstrates the use of a genetic algorithm to optimize airframe sizing for model airplanes.
Building MATLAB Apps with App Designer Build apps with MATLAB to automate repetitive interactive code. Sebastian Castro and Connell D'Souza from the Robotics Arena demonstrate building interactive apps using App Designer.
Distributed Computing with MATLAB, Simulink, and ROS Join Sebastian Castro and Connell D’Souza as they discuss techniques in Simulink to design and deploy multirate and multiplatform robotics algorithms with the Robot Operating System (ROS).
Designing Robot Manipulator Algorithms Accelerate the design of robot manipulator algorithms by using the Robotics Systems Toolbox functionality and integrating robot models with simulation tools to program and test manipulation tasks.
Designing Digital Filters with MATLAB Join Mark Schwab and Connell D'Souza as they demonstrate the use of the Filter Designer app and interactively design filters for digital signal processing that can be implemented in MATLAB or Simulink.
System Identification of Blue Robotics Thrusters Create a model for a piece of hardware from input and output data using the System Identification app. Connell D'Souza and Kris Fedorenko explain the workflow from data gathering to model evaluation.
Controlling Robot Manipulator Joints Learn how MATLAB, Simulink, and Robotics System Toolbox can help you design joint torque controllers for robotic manipulation and grasping tasks.
Simulating Mobile Robots with MATLAB and Simulink Learn how to work with the Mobile Robotics Simulation Toolbox on the MATLAB Central File Exchange.
MATLAB Apps with ROS Learn how to design interactive MATLAB apps to communicate with ROS enabled robots and simulators.
Robotics Education with MATLAB and Simulink Professor Peter Corke and Sebastian Castro discuss how MATLAB and Simulink can be used in robotics education.
Programming Robot Swarms Explore how to use MATLAB and Simulink for prototyping and implementation of robot swarm behavior.
Labeling Ground Truth for Object Detection Use the Ground Truth Labeler app to generate quality ground truth data that can be used to train and evaluate object detectors.
Training and Validating Object Detectors Use labeled ground truth data to train and evaluate object detectors.
Deep Learning with MATLAB, NVIDIA Jetson, and ROS Learn how GPU Coder can be used to deploy deep learning algorithms from MATLAB to embedded NVIDIA GPUs, and how the deployed code can be used with the Robot Operating System (ROS).
Sensor Fusion for Orientation Estimation Join Roberto Valenti and Connell D’Souza as they discuss using Sensor Fusion and Tracking Toolbox to perform sensor fusion for orientation estimation.
Simulating Pneumatic Robot Actuators Veer and Maitreyee show how you can model a pneumatic system by using physical blocks available in Simscape.
Simulating Robot Throwing Mechanisms Veer and Maitreyee show you how to build a throwing mechanism to throw a ball at a certain target using Simscape Multibody.
Control Design for Robot Throwing Systems Veer and Maitreyee first show how you can extend Simscape Multibody throwing mechanism models with physical effects modeled in Simscape. Later, controller is implemented in the system to track the reference piston position.
Autopilot Development Using Simulink Claudio Conti of Sapienza Flight Team at Sapienza University of Rome joins Connell D’Souza to talk about using Model-Based Design and Real-Time Simulation to design a custom autopilot.
LQR Control of an Autonomous Underwater Vehicle Learn the basics of implementing a Linear-Quadratic Regulator (LQR) controller for an autonomous underwater vehicle with Juan Rojas and Nathan Liebrecht of the Autonomous Robotic Vehicle Project.
Deep Reinforcement Learning for Walking Robots Use MATLAB, Simulink, and Reinforcement Learning Toolbox to train control policies for humanoid robots using deep reinforcement learning.
Programming Soccer Robot Behavior Explore how to use MATLAB and Simulink for prototyping and implementation of multiagent systems through an autonomous soccer robot example.
Walking Robot Pattern Generation Learn how MATLAB and Simulink can be used to design walking pattern generators for legged humanoid robots.
Programming BeagleBone Blue with Simulink Sebastian Castro and Kurt Talke introduce the BeagleBone Blue hardware and demonstrate how it can be programmed using Simulink for robotics applications.
Trajectory Planning for Robot Manipulators Sebastian Castro discusses how MATLAB and Simulink can help you design, plan, and verify motion trajectories for robot manipulation tasks.
Model-Based Control of Humanoid Walking Learn how the linear inverted pendulum model (LIPM) can be used to design humanoid walking patterns in MATLAB and Simulink.
Learning Robotics with MATLAB and Simulink Learn how you can use MATLAB and Simulink to teach robotics for primary and secondary schools, using both simulation and low-cost educational hardware.
Modeling and Simulation of Walking Robots Learn how to model a bipedal walking robot using Simscape, including physical contact forces, actuator models, and controllers.
Data Preprocessing for Deep Learning Learn how to resize images, create labeled training, validation, and test datasets to train and test object detection models, as Neha Goel joins Connell D’Souza to talk about data preprocessing for deep learning.
Design and Train a YOLOv2 Network in MATLAB Neha Goel joins Connell D’Souza to talk about designing and training a YOLOv2 real-time object detection neural network.
Import Pretrained Deep Learning Networks into MATLAB Neha Goel joins Connell D’Souza to demonstrate how to use Open Neural Network Exchange (ONNX) to import pretrained deep learning networks into MATLAB and perform transfer learning.
Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .Select web site
You can also select a web site from the following list:
Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.